Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Adjust dropout, depth and multi-task in parser

This commit is contained in:
Matthew Honnibal 2017-05-24 20:11:41 -05:00
parent e6cc927ab1
commit e1cb5be0c7
1 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/syntax/nn_parser.pyx
View File

@ -416,7 +416,9 @@ cdef class Parser:
free(scores)
free(token_ids)
def update(self, docs_tokvecs, golds, drop=0., sgd=None):
def update(self, docs_tokvecs, golds, drop=0., sgd=None, losses=None):
if losses is not None and self.name not in losses:
losses[self.name] = 0.
docs, tokvec_lists = docs_tokvecs
tokvecs = self.model[0].ops.flatten(tokvec_lists)
if isinstance(docs, Doc) and isinstance(golds, GoldParse):
@ -436,17 +438,19 @@ cdef class Parser:
backprops = []
d_tokvecs = state2vec.ops.allocate(tokvecs.shape)
cdef float loss = 0.
while len(todo) >= 3:
while len(todo) >= 2:
states, golds = zip(*todo)
token_ids = self.get_token_ids(states)
vector, bp_vector = state2vec.begin_update(token_ids, drop=0.0)
if drop != 0:
mask = vec2scores.ops.get_dropout_mask(vector.shape, drop)
vector *= mask
scores, bp_scores = vec2scores.begin_update(vector, drop=drop)
d_scores = self.get_batch_loss(states, golds, scores)
d_vector = bp_scores(d_scores, sgd=sgd)
if drop != 0:
d_vector *= mask
if isinstance(self.model[0].ops, CupyOps) \
@ -461,10 +465,12 @@ cdef class Parser:
backprops.append((token_ids, d_vector, bp_vector))
self.transition_batch(states, scores)
todo = [st for st in todo if not st[0].is_final()]
if len(backprops) >= 50:
if len(backprops) >= 20:
self._make_updates(d_tokvecs,
backprops, sgd, cuda_stream)
backprops = []
if losses is not None:
losses[self.name] += (d_scores**2).sum()
if backprops:
self._make_updates(d_tokvecs,
backprops, sgd, cuda_stream)